EPSCoR Research Fellows: NSF: Multiphysics Computational Framework and Reinforcement Learning for Compressible Flows
Ente: EPSCoR RII: EPSCoR Research Fe
Scadenza: 2028-04-30
Importo max: 300.000 EUR
Paese: US
Descrizione
This Research Infrastructure Improvement (RII) EPSCoR Research Fellows project provides a fellowship to an Assistant Professor and training for a graduate student at Auburn University. This work is conducted in collaboration with researchers at Los Alamos National Laboratory (LANL). Through the fellowship, the principal investigator (PI) will develop high-fidelity, massively parallel computational tools to enable robust simulations of fluid-structure interactions and turbulent combustion. The flow data generated from the proposed simulations will be utilized to construct a machine learning (ML) algorithm to control flow behavior. The project integrates applied mathematics, fluid dynamics, and artificial intelligence to develop numerical tools that will reduce the cost and improve the accuracy of computational methodologies for aircraft and spacecraft design. The developed tools will help alleviate the dependency on expensive wind tunnel and flight tests in transonic and supersonic regimes. The project will also help train a graduate student on applying ML to fluid dynamics.
This project will implement high-order numerical methods for execution on heterogeneous supercomputing platforms to conduct fluid-structure interaction (FSI) simulations in practical domains at transonic/supersonic flow conditions. The complex geometries and moving boundaries of interest in engineering applications make it challenging to ensure high-order solution accuracy without prohibitive computational cost. This study will leverage the computing expertise and resources at LANL to integrate and implement adaptive mesh refinement with cut-cell methodology, developed by the PI, helping enable scale-resolving FSI simulations in flow regimes that have been computationally intractable so far. Furthermore, a flow control strategy based on deep reinforcement learning will be tested to mitigate the adverse FSI effects. The fellowship will help the PI establish a strong multiphysics computational research program to train graduate and undergraduate researchers in Alabama for fundamental flow physics investigations in aerodynamics and propulsion. This long-term capability will allow meaningful collaborations with NASA Marshall and the Propulsion Research Center at the University of Alabama Huntsville. This project is supported by the EPSCoR Research Infrastructure Improvement Program: EPSCoR Research Fellows, which supports early- and mid-career investigators in eligible jurisdictions to develop collaborations at the nation’s private, government or academic research institutions.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
Istituzione: Auburn University
Sede: AUBURN, AL
PI: Nek Sharan
Settori: EPSCoR RII: EPSCoR Research Fe
Vai al bando originale
Registrati gratis su Bandolo per trovare bandi compatibili con la tua azienda.